Hi all. I’m learning Machine Learning with TensorFlow. But , i got a trouble with Validation Split when i used model.fit() API.
It gave me a log that is:
Traceback (most recent call last):
File "c:\Users\dell\OneDrive - khang06\My-Workspace\Programming\CLB-Stem-TamPhu\KhoaHocKyThuat-THPT-TamPhu\MachineLearning\Multi-class-Classification\Multi-class-Classification.py", line 84, in <module>
epochs , hist = train_model(my_model , x_train_normalized , y_train,
File "c:\Users\dell\OneDrive - khang06\My-Workspace\Programming\CLB-Stem-TamPhu\KhoaHocKyThuat-THPT-TamPhu\MachineLearning\Multi-class-Classification\Multi-class-Classification.py", line 48, in train_model
history = model.fit(x=train_features , y=train_model, batch_size=batch_size , epochs=epochs , shuffle=True ,
File "C:\Users\dell\OneDrive - khang06\My-Workspace\TSC\lib\site-packages\keras\utils\traceback_utils.py", line 70, in error_handler
raise e.with_traceback(filtered_tb) from None
File "C:\Users\dell\OneDrive - khang06\My-Workspace\TSC\lib\site-packages\keras\engine\data_adapter.py", line 1664, in train_validation_split
raise ValueError(
ValueError: `validation_split` is only supported for Tensors or NumPy arrays, found following types in the input: [<class 'function'>]
Could u please help me to resolve it? Thanks a lot.
The key thing in that error message is the last line:
So somewhere you are passing in a function rather than the actual data the function is providing. It’s hard to say exactly what’s wrong without seeing your code, but you could be doing something like this:
data = load_data
model.fit(data, validation_split=0.1)
instead of
data = load_data()
model.fit(data, validation_split=0.1)
If its still not obvious, share your code specifically around loading data
1 Like
Oh my bad 
, i’m really sorry for the lack of information.
Here is my code:
from venv import create
import numpy as np
import pandas as pd
import tensorflow as tf
from matplotlib import pyplot as plt
pd.set_option("display.max_rows" , 10)
pd.set_option("display.float_format" , "{:.1f}".format)
np.set_printoptions(linewidth= 200)
(x_train , y_train) , (x_test , y_test) = tf.keras.datasets.mnist.load_data()
def create_model(my_learning_rate):
"""Create and compile a deep neural net."""
model = tf.keras.models.Sequential()
# The features are stored in a two-dimensional 28X28 array.
# Flatten that two-dimensional array into a one-dimensional
# 784-element array.
model.add(tf.keras.layers.Flatten(input_shape=(28,28)))
# Define the first hidden layer
model.add(tf.keras.layers.Dense(units=32 , activation='relu'))
# Define a dropout regularization layer.
model.add(tf.keras.layers.Dropout(rate=0.2))
# Define the output layer. The units parameter is set to 10 because
# the model must choose among 10 possible output values (representing
# the digits from 0 to 9 , inclusive)
#
# Don't change this layer
model.add(tf.keras.layers.Dense(units=10 , activation='softmax'))
# Construct the layers into a model that TensorFlow can execute.
# Notice that the loss function for multi-class classification
# is different than the loss function for binary classification
model.compile(optimizer=tf.keras.optimizers.Adam(learning_rate=my_learning_rate) ,
loss="sparse_categorical_crossentropy" ,
metrics=['accuracy'])
return model
def train_model(model , train_features , train_label , epochs ,
batch_size=None , validation_split=0.1):
"""Train the model by feeding it data"""
history = model.fit(x=train_features , y=train_model, batch_size=batch_size ,
epochs=epochs , shuffle=True ,
validation_split=validation_split)
# To track the progression of training , gather a snapshot
# of the model's metrics at each epoch.
epochs = history.epoch
hist = pd.DataFrame(history.history)
return epochs , history
def plot_curve(epochs , hist , list_of_metrics):
"""Plot a curve of one or more classification metrics vs. epoch"""
plt.figure()
plt.xlabel("Epoch")
plt.ylabel("Value")
for m in list_of_metrics:
x = hist[m]
plt.plot(epochs[1:] , x[1:] , label=m)
plt.legend()
if __name__ == '__main__':
learning_rate = 0.003
epochs = 50
batch_size = 4000
validation_split = 0.2
x_train_normalized = x_train / 255.0
x_test_normalized = x_test / 255.0
# Establish the model's topography
my_model = create_model(learning_rate)
# Train the model on the normalized training set.
epochs , hist = train_model(my_model , x_train_normalized , y_train,
epochs , batch_size , validation_split)
# Plot a graph of the metric vs. epochs
list_of_metrics_to_plot = ['accuracy']
plot_curve(epochs , hist , list_of_metrics_to_plot)
# Evaluate against the test set
print("\n Evaluate the new model against the test set:")
my_model.evaluate(x=x_test_normalized , y=y_test , batch_size=batch_size)
Can u help me to fix it Thanks a lot
ok, here’s your problem:
def train_model(model, train_features, train_label, epochs,
batch_size=None, validation_split=0.1):
"""Train the model by feeding it data"""
history = model.fit(x=train_features, y=train_model, batch_size=batch_size,
epochs=epochs, shuffle=True,
validation_split=validation_split)
You can see this is a function called train_model() and you are passing that into model.fit() with y=train_model. This should be train_label (I guess?)
1 Like
oh my gah , thanks a lot why i didnt see this mistake , it’s so eazy to see my bad , thank u a lot.